AI Red Teaming Lab for RAG Security Testing with Promptfoo

AI Red Teaming Lab for RAG Security Testing with PromptfooAI Red Teaming Lab for RAG Security Testing with Promptfoo

The network for creativity

Join 1.25M professional creatives like you

Connect with clients, get discovered, and run your business 100% commission-free

Creatives on Contra have earned over $150M and we are just getting started

Back to feedPost

Stephen Kisong'e

• Sep 28

Built a controlled Kiso Secure AI red teaming lab using Promptfoo to test a local RAG application for prompt injection, system prompt leakage, indirect prompt injection, and sensitive data exposure. The setup used AnythingLLM with a Kiso Secure knowledge base, automated adversarial testing, and a hardened workspace to compare security behavior before and after remediation.

Completed work

AI Automation Cybersecurity Security Engineering npm PyTorch TensorFlow

Johnson Afolabi

• 2d

Running Promptfoo to hunt prompt injection saves a lot of manual probing and gives clear before and after metrics

Stephen Kisong'e

• 1d

Sure, and it gives a compliance mapping and reporting across regulatory standards like the EU AI Act, NIST AI RMF, and the OWASP Top 10 for LLM

Talha Ishtiaq

• Sep 26

Built this AI agent to find, organize, and manage leads through Gmail, helping automate lead handling and outreach.

Completed work

AI Agent Designer AI Agent Development AI Agent Engineer N8N

Muhammad Sohaib

• Sep 28

n8n is absolute gold for orchestrating lead pipelines like this! Connecting Gmail parsing with LLM qualification saves teams dozens of hours weekly. As someone who builds custom agentic lead automation workflows, seeing clean visual architectures like this is super satisfying. Top-tier build, Talha!.